Getting started

PicoBerry API Reference

A resource-oriented REST API for programmatic 3D and image generation — text-to-image, text/image-to-3D, plus remesh, texture, and auto-rig on any asset you create.

Base URLhttps://api.picoberry.ai
Versionv1
AuthBearer / x-api-key

The API accepts JSON (and multipart/form-data for file uploads), returns JSON, uses standard HTTP status codes, and wraps every response in a { success, data } envelope. Generation is asynchronous: a create call returns an asset id; you poll or receive a webhook when it finishes.

Start here

Endpoint overview

Everything lives under https://api.picoberry.ai/v1. Generation is asynchronous — a create call returns an id you poll or receive by webhook; post-process calls take that same id.

EndpointPurpose
POST /v1/imagesText → Image
POST /v1/models/from-textText → 3D
POST /v1/models/from-imageImage, or 2–4 views, → 3D
POST /v1/images/parts-boardDecompose an image into parts
POST /v1/assets/{id}/remeshRetopologize a model
POST /v1/assets/{id}/textureRe-texture a model
POST /v1/assets/{id}/animateAuto-rig & animate
POST /v1/assets/{id}/downloadExport GLB / FBX / OBJ (sync)
GET /v1/assets/{id}Poll status & fetch results
GET /v1/assetsList your assets
GET /v1/modelsEngine catalog & per-model cost
GET /v1/creditsWallet balance & plan
POST /v1/collectionsOrganize assets into collections

Libraries

One API, every engine

Pick a generation engine per request — tripo, meshy, hunyuan-3.1, trellis-2 for 3D; nano-banana, gpt-image for images. The catalog and exact per-model cost are authoritative via GET /v1/models.